• 터널과지하공간
• /
• 제31권6호
• /
• pp.494-507
• /
• 2021

TBM의 활용이 증가하면서 최근 국내에서도 머신러닝 기법으로 TBM 데이터를 분석하여 TBM 전방의 지반을 예측하고 디스크커터의 교환주기 예측 및 굴진율을 예측하는 연구가 수행되고 있다. 본 연구에서는 TBM 굴진 시 기계 데이터를 대상으로 전통적 암반에 대한 분류 기법과 최근에 다양한 분야에서 널리 사용되고 있는 머신러닝 기법들을 접목하여 슬러리 쉴드 TBM 현장의 암반 특성에 대한 분류 예측을 하였다. 암반 특성 분류 기준 항목을 RQD, 일축압축강도, 탄성파속도로 설정하고 항목별 암반상태를 클래스 0(양호),1(보통),2(불량)의 3개 클래스로 구분한 다음, 6개의 분류 알고리즘에 대한 기계학습을 수행하였다. 그 결과, 앙상블 계열의 모델이 좋은 성능을 보여주었고 특히 학습성능과 더불어 학습속도에서 우수한 결과를 보인 LigthtGBM 모델이 대상 현장 지반에서 최적인 것으로 나타났다. 본 연구에서 설정한 3가지 암반 특성에 대한 분류 모델을 활용하면 지반정보가 제공되지 않은 구간에 대한 암반 상태를 제공할 수 있어 굴착작업 시 도움을 줄 수 있을 것으로 판단된다.

• 터널과지하공간
• /
• 제32권6호
• /
• pp.502-517
• /
• 2022

TBM의 활용이 증가하면서 최근 국내외에서 머신러닝 기법으로 TBM 데이터를 분석하여 디스크커터의 교환주기 예측 및 굴진율을 예측하는 연구가 증가하고 있다. 본 연구에서는 굴진 시 획득되는 기계 데이터와 지반 데이터를 기반으로 최근에 다양한 분야에서 널리 사용되고 있는 머신러닝 기법들 중 회귀 모델을 접목하여 슬러리 쉴드 TBM 현장의 디스크 커터 마모 예측을 하였다. 디스크 커터 마모 예측을 위해서 Training과 Test 데이터를 7:3으로 분할하였으며, 최적의 파라미터를 선정을 위해서 분할 교차검증을 포함하는 그리드 서치를 활용하였다. 그 결과, 앙상블 계열의 그레디언트 부스팅 모델이 결정계수가 0.852, 평균 제곱근 오차가 3.111로 좋은 성능을 보여주었고 특히 학습성능과 더불어 학습속도에서 우수한 결과를 보여주었다. 현재 도출된 결과로 볼 때, 슬러리 쉴드 TBM의 기계데이터와 지반정보가 포함된 데이터를 활용한 디스크 커터 마모 예측 모델의 적합성은 높다고 보인다. 추가적으로 지반조건의 다양성과 디스크 마모 측정 데이터양을 늘리는 연구가 필요한 것으로 판단된다.

• 한국건축시공학회지
• /
• 제9권4호
• /
• pp.75-83
• /
• 2009

현재 기계굴착공법인 올케이싱, 어스 드릴, 역순환공법이 널리 활용되고 있음에도 불구하고, 시공 현장에서 발생되는 부조화로 인하여 말뚝의 품질이 저하되거나 부실시공이 빈번히 발생되고 있다. 본 연구에서는 이 문제를 줄이는 방법으로 올케이싱, 어스 드릴, 역순환공법을 중심으로 현장 콘크리트타설 말뚝 시공시 발생되는 부조화 종류별로 부조화 발생요인을 현장기술자들을 대상으로 설문조사를 수행 하였다. 그리고 설문분석결과를 토대로 부조화 종류별로 빈번히 발생되는 부조화 요인을 분석함으로서 대응방안을 제시하였다. 본 연구에서 분석된 자료는 향후 건설현장에서 기계굴착공법으로 시공될 때, 부조화를 최소화 할 수 있는 효과적인 자료가 될 것으로 사료된다.

• 대한안전경영과학회지
• /
• 제6권3호
• /
• pp.15-26
• /
• 2004

There is much dangerous machine in worksite. These make the rate of accidents increase. Specially, among them, dryness equipment work has the highest rate of accidents. Therefore, it has been managed by safety-health law. It is very important to make a special study of work using the dangerous machine. In press work, it is also important to develop safety system program to improve productivity and work safely In this reaserch. the safety mangement system is built for the work improvement of the Press. I will try new development method about dangerous machine.

• 한국건축시공학회지
• /
• 제7권3호
• /
• pp.67-73
• /
• 2007

Increasing wages and decreasing skilled labors are problems awaiting solution. The development of automatic technologies contributes to accelerating the one of construction automation. Thus, this study is to suggest the way to develop the automated building construction system base on one performed in Japan in order to solve urgent problems of construction industry in Korea. Therefore interviews and questionnaires were performed based on experts who work for the automated building construction system field and analyzed through analytic hierarchy process. In doing so, it was the most important factor to develop a branch of automatic, mechanical or machine technologies for the automated building construction system. Especially the study indicated the importance of the technologies to substitute skilled labors such as a robot. This research could contribute to developing the automated building construction which is very unique and suitable for construction industry in Korea.

• Structural Engineering and Mechanics
• /
• 제63권1호
• /
• pp.115-124
• /
• 2017

In this paper, a different technique to predict the effects of soil-structure interaction (SSI) on seismic response of building systems is investigated. The technique use a machine learning algorithm called Support Vector Regression (SVR) with technical and analytical results as input features. Normally, the effects of SSI on seismic response of existing building systems can be identified by different types of large data sets. Therefore, predicting and estimating the seismic response of building is a difficult task. It is possible to approximate a real valued function of the seismic response and make accurate investing choices regarding the design of building system and reduce the risk involved, by giving the right experimental and/or numerical data to a machine learning regression, such as SVR. The seismic response of both single-degree-of-freedom system and six-storey RC frame which can be represent of a broad range of existing structures, is estimated using proposed SVR model, while allowing flexibility of the soil-foundation system and SSI effects. The seismic response of both single-degree-of-freedom system and six-storey RC frame which can be represent of a broad range of existing structures, is estimated using proposed SVR model, while allowing flexibility of the soil-foundation system and SSI effects. The results show that the performance of the technique can be predicted by reducing the number of real data input features. Further, performance enhancement was achieved by optimizing the RBF kernel and SVR parameters through grid search.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2015년도 춘계 학술논문 발표대회
• /
• pp.121-122
• /
• 2015

The demand on free-form buildings is gradually increasing, but there are several problems such as increased cost and construction duration, and decreased constructability at the construction phase upon construction of a building owing to the difficulty of member production-installation. To solve these problems, a technology to produce FCP using a CNC machine was developed. Basically, it delivers the information on a free-form building designed to the CNC machine, the shapes of RTM and PCM are created using the information delivered and FCP are produced with the RTM and PCM which act as forms. Since the construction duration and project cost are limited on site, the efficiency of FCP production-installation is significant for application of the technology. For it is almost impossible to change the production-installation layout and process once they are set in the construction phase, they should be carefully determined. Before the production-installation layout are established, it is necessary to analyze the factors that influence the duration. Thus, the study intends to analyze influence factors in PCM mold on estimation of the production-installation duration for FCP. According to the analysis of influence factors, a simulation model for estimation of the duration that changes depending on the constraint conditions can be built.

• Structural Engineering and Mechanics
• /
• 제71권3호
• /
• pp.317-327
• /
• 2019

The aim of this paper is to present the most important issues on the implementation, operation and maintenance of foundation for machines. The article presents the newest solutions both in terms of technology implementation as well as materials used in construction of such structures. Foundations for machines are special building structures used to transfer loads from an operating machine to the subsoil. The purpose of these foundations is not just to transfer loads, but also to reduce vibrations occurring during operation of the machine, i.e. their damping and preventing redistribution to other elements of the building. It should be noted that foundations for machines (particularly foundations for hammers) are the most dynamically loaded building structures. For these reasons, they require precise static and dynamic calculations, accuracy in their implementation and care for them after they have been made. Therefore, the paper in detail present the guidelines regarding: design, construction and maintenance of structures of this type. Furthermore, the most important parameters and characteristics of materials used for the construction of these foundations are described. As a result of the conducted analyzes, it was found that the concrete mix, in foundations for machines, should have a low water/binder ratio. For its execution, it is necessary to use broken aggregates from igneous rocks and binders modified with mineral additives and chemical admixtures. On the other hand, the reinforcement of composites should contain a large amount of structural reinforcement to prevent shrinkage cracks.

• 대한건축학회논문집:구조계
• /
• 제35권2호
• /
• pp.45-52
• /
• 2019

BEMS(Building Energy Management Systems) have been applied to office buildings and collect relevant building energy data, e.g. temperatures, mass flow rates and energy consumptions of building mechanical systems and indoor spaces. The aforementioned measured data can be beneficially utilized for developing data-driven machine learning models which can be then used as part of MPC(Model Predictive Control) and/or optimal control strategies. In this study, the authors developed ANN(Artificial Neural Network) models of an AHU (Air Handling Unit) and a chiller for a real-life office building using BEMS data. Based on the ANN models, the authors developed optimal control strategies, e.g. daily operation schedule with regard to optimal start and stop of the AHU and the chiller (500 RT). It was found that due to the optimal start and stop of the AHU and the chiller, 4.5% and 16.4% of operation hours of the AHU and the chiller could be saved, compared to an existing operation.

• 건설관리
• /
• 제22권2호
• /
• pp.17-20
• /
• 2021